Method and apparatus for processing data using calculators having different degrees of accuracy

Abstract

A method of processing data includes classifying input data into first data and second data, the second data being different from the first data, separately compiling the first data and the second data, and providing the compiled first data and the compiled second data to a first operator and a second operator, respectively, in which the first operator performs an operation different from an operation performed by the second operator.

What is claimed is: 
     
         1 . A method of processing data, the method comprising:
 classifying input data into first data and second data, the second data being different from the first data;   separately compiling the first data and the second data; and   providing the compiled first data and the compiled second data to a first operator and a second operator, respectively,   wherein the first operator performs an operation different from an operation performed by the second operator.   
     
     
         2 . The method of  claim 1 , wherein, the compiling of the first data and second data comprises compiling the first data by using a first instruction set architecture (ISA) included in a compiling unit and compiling the second data by using a second ISA included in the compiling unit. 
     
     
         3 . The method of  claim 2 , wherein the first ISA uses the first operator and the second ISA uses the second operator. 
     
     
         4 . The method of  claim 1 , wherein the input data comprises a shader code for rendering an object. 
     
     
         5 . The method of  claim 1 , further comprising determining the first data based on a keyword included in the input data. 
     
     
         6 . The method of  claim 1 , wherein the operation performed by the first operator on the first data has an error rate lesser than an error rate of the operation performed by the second operator on the second data. 
     
     
         7 . The method of  claim 1 , wherein the first data comprises data indicating a position of an object to be rendered. 
     
     
         8 . The method of  claim 1 , wherein the second data comprises data indicating a color of an object. 
     
     
         9 . The method of  claim 1 , wherein the operation performed by the second operator is performed by using a polynomial expression obtained based on an approximation of a predetermined function. 
     
     
         10 . The method of  claim 1 , wherein each of the first operator and the second operator comprises an operator that operates a number represented by using a floating point method. 
     
     
         11 . A non-transitory computer readable storage medium having stored thereon a program, which when executed by a computer, performs the method of  claim 1 . 
     
     
         12 . An apparatus for processing input data, the apparatus comprises:
 a compiling unit configured to classify the input data into first data and second data, the second data being different from the first data, and to separately compile the first data and the second data; and   an operation unit comprising a first operator configured to perform an operation based on the compiled first data and a second operator configured to perform an operation based on the compiled second data,   wherein the operation performed by the first operator is different from the operation performed by the second operator.   
     
     
         13 . The apparatus of  claim 12 , wherein the compiling unit is further configured to compile the first data by using a first instruction set architecture (ISA) and compiles the second data by using a second ISA. 
     
     
         14 . The apparatus of  claim 13 , wherein the first ISA uses the first operator and the second ISA uses the second operator. 
     
     
         15 . The apparatus of  claim 12 , wherein the input data comprises a shader code for rendering an object. 
     
     
         16 . The apparatus of  claim 12 , further comprising a determination unit configured to determine the first data based on a keyword included in the input data. 
     
     
         17 . The apparatus of  claim 12 , wherein the operation performed by the first operator on the first data is has an error rate lesser than an error rate of the operation performed by the second operator on the second data. 
     
     
         18 . The apparatus of  claim 12 , wherein the first data comprises data indicating a position of an object to be rendered. 
     
     
         19 . The apparatus of  claim 12 , wherein the second data comprises data indicating a color of an object. 
     
     
         20 . The apparatus of  claim 12 , wherein the operation performed by the second operator is performed by using a polynomial expression obtained based on an approximation of a predetermined function. 
     
     
         21 . The apparatus of  claim 12 , wherein each of the first operator and the second operator comprises an operator that operates a number represented by using a floating point method. 
     
     
         22 . A compiler for providing data to a processor comprising a plurality of operators, wherein the compiler is configured to:
 classify the data into first data and second data, the second data being different from the first data, and separately compile the first data and the second data; and   provide the compiled first data and the compiled second data to a first operator and a second operator, respectively,   wherein the operation performed by the first operator is different from the operation performed by the second operator.   
     
     
         23 . An operation apparatus comprising:
 a first operator configured to perform an operation by using first data provided by a compiler; and   a second operator configured to perform an operation by using second data provided by the compiler,   wherein the operation performed by the first operator is different from the operation performed by the second operator.